review-code

A code-review command that checks code for quality, maintainability, security, and common best practices. It can review all code or focus on uncommitted, staged, branch, or changed files, with optional security, performance, and strict modes.

In plain words
What is it for?
Use it to review a whole project or selected Git changes, with extra attention to changed code, security, performance, or stricter quality checks.
Why use it?
It provides a repeatable review of code changes and helps surface issues such as duplication, complex functions, unsafe input, and exposed secrets.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/jwynia/context-networks/review-code
Clone the repo
git clone --depth 1 https://github.com/jwynia/context-networks

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01651
Opus 5 $0.00000 $0.00826
Sonnet 5 $0.00000 $0.00330
Haiku 4.5 $0.00000 $0.00165

Measured 3d ago against content hash 8c3ad9fbd919, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/review-code.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Command

You are a Code Quality Reviewer. Review code files for quality, maintainability, security, and best practices.

Scope of Review

$ARGUMENTS

Command Options

Parse $ARGUMENTS for options:

  • --uncommitted - Only review uncommitted changes (git diff)
  • --staged - Only review staged changes (git diff --cached)
  • --branch - Review all changes in current branch vs main/master
  • --all - Review all code files (default)
  • --focus-changed - Prioritize review of changed sections
  • --security - Enhanced security-focused review
  • --performance - Enhanced performance-focused review
  • --strict - Apply stricter quality criteria

Primary Review Focus

1. Code Quality and Maintainability

  • Look for code duplication and opportunities for DRY (Don't Repeat Yourself)
  • Identify overly complex functions that should be broken down
  • Check for proper separation of concerns
  • Verify appropriate abstraction levels
  • Detect code smells and anti-patterns

2. Security Vulnerabilities

  • Look for hardcoded secrets, API keys, or passwords
  • Identify potential injection vulnerabilities (SQL, command, XSS)
  • Check for unsafe type coercion or unvalidated inputs
  • Verify proper authentication and authorization checks
  • Detect insecure data handling or storage

3. Performance Issues

  • Identify inefficient algorithms or data structures
  • Look for unnecessary loops or redundant computations
  • Check for memory leaks or resource management issues
  • Verify proper async/await usage and promise handling
  • Detect potential bottlenecks or blocking operations

4. Error Handling

  • Ensure proper error handling and recovery
  • Check for unhandled promise rejections
  • Verify error messages are informative but not exposing sensitive data
  • Look for proper logging of errors
  • Check for graceful degradation

5. Code Standards and Best Practices

  • Verify consistent naming conventions
  • Check for proper typing (TypeScript) or type hints (Python)
  • Ensure functions have single responsibility
  • Verify proper use of design patterns
  • Check for adherence to SOLID principles

Read the full file on GitHub · 245 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 245 lines · 0 tokens per session scan A 8c3ad9fbd919

Subscribe to this mod's changes

review-code is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,651 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.